RecFlow: Unlocking GPU Efficiency for DLRM Inference via Fine-Grained Parallelism and Incremental Batching - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Siheng Pan, Shaolong Li, Minwei Zhang, Shuxi Guo, Haifeng Sun 0001, Qi Qi 0001, Zirui Zhuang, Xiang Yang, Chunyang Jiang, Jianxin Liao, Jing Wang 0039. RecFlow: Unlocking GPU Efficiency for DLRM Inference via Fine-Grained Parallelism and Incremental Batching. In IEEE INFOCOM 2026 - IEEE Conference on Computer Communications, Tokyo, Japan, May 18-21, 2026. pages 1-10, IEEE, 2026. [doi]

This author has not been identified. Look up 'Siheng Pan' in GoogleThis author has not been identified. Look up 'Shaolong Li' in GoogleThis author has not been identified. Look up 'Minwei Zhang' in GoogleThis author has not been identified. Look up 'Shuxi Guo' in GoogleThis author has not been identified. Look up 'Haifeng Sun 0001' in GoogleThis author has not been identified. Look up 'Qi Qi 0001' in GoogleThis author has not been identified. Look up 'Zirui Zhuang' in GoogleThis author has not been identified. Look up 'Xiang Yang' in GoogleThis author has not been identified. Look up 'Chunyang Jiang' in GoogleThis author has not been identified. Look up 'Jianxin Liao' in GoogleThis author has not been identified. Look up 'Jing Wang 0039' in Google

runs on WebDSL